Cover not available
Part of
Corpus Use in Cross-linguistic Research: Paving the way for teaching, translation and professional communication
Edited by Marlén Izquierdo and Zuriñe Sanz-Villar
[Studies in Corpus Linguistics 113] 2023
► pp. 179–194

Chapter 10
Domain-adapting and evaluating machine translation for institutional German in South Tyrol

| University of Bologna
| Eurac Research, Institute for Applied linguistics

Building on a prior small-scale study on machine translation adaptation in the same language pair and domain (De Camillis 2021), this chapter reports on a (i) domain-adaptation, (ii) quality assessment, and (iii) automatic legal terminology evaluation experiment for legal South Tyrolean German. After collecting, sentence-aligning, and cleaning the LEXB parallel corpus, we used this bilingual resource to domain-adapt a ModernMT engine. Performance improvements were measured in terms of automatic quality metrics. The machine-translation of South Tyrolean legal terms was evaluated using an ad hoc automatic terminology evaluation tool. We observed a significant boost in performance and term accuracy in the output of the ModernMT adapted engine, but the improvement in legal terminology translation was deemed unsatisfactory.

Keywords: machine translation adaptation, legal terminology, institutional language, machine translation evaluation
Article outline
  • 1.Introduction
  • 2.German in South Tyrol
  • 3.Previous experiments on MT and legal German
  • 4.Methodology
    • 4.1Corpus building
    • 4.2MT adaptation and testing
    • 4.3Automatic terminology evaluation
  • 5.Results
  • 6.Conclusions
  • Notes
  • References
Published online: 2 November 2023
DOI logo
https://doi.org/10.1075/scl.113.10con
References
Alam, Md Mahfuz ibn, Anastasopoulos, Antonios, Besacier, Laurent, Cross, James, Gallé, Matthias, Koehn, Philipp & Nikoulina, Vassilina
2021 On the evaluation of machine translation for terminology consistency. ArXiv:2106.11891 [Cs]. [URL]Google Scholar
Beller, Manfredi & Leerssen, Joep
(Eds) Imagology: The Cultural Construction and Literary Representation of National Characters, Studia Imagologica Vol. 13, Amsterdam & New York: Rodopi 2007Google Scholar
Bertoldi, Nicola, Caroselli, Davide & Federico, Marcello
2018 The ModernMT project. In Proceedings of the 21st Annual Conference of the European Association for Machine Translation, Juan Antonio Pérez-Ortiz, Felipe Sánchez-Martínez, Miquel Esplà-Gomis, Maja Popović et al. (eds), 345. Alicante: European Association for Machine Translation. [URL] (30 May 2023).
Callison-Burch, Chris, Osborne, Miles & Koehn, Philipp
2006 Re-evaluating the role of Bleu in machine translation research. In Proceedings of the 11th Conference of the European Chapter of the Association for Computational Linguistics, Diana McCarthy & Shuly Wintner (eds), 249–256 Trento: Association for Computational Linguistics.
Chiocchetti, Elena, Kranebitter, Klara, Ralli, Natascia & Stanizzi, Isabella
2013 Deutsch ist nicht gleich Deutsch. Eine terminologische Analyse zu den Besonderheiten der deutschen Rechtssprache in Südtirol. In Diatopische Variation in der deutschen Rechtssprache, Marina Marzia Brambilla, Joachim Gerdes, & Chiara Messina (eds), 253–285. Berlin: Frank & Timme. [URL]> (30 May 2023).Google Scholar
Chiocchetti, Elena
2019a Legal comparison in terminology work: Developing the South Tyrolean German legal language. In Diszciplínák találkozása: Nyelvi közvetítés a XXI. században, Szilvia Szoták (ed.), 175–185. Budapest: OFFI.Google Scholar
2019b Terminology work in South Tyrol: New approaches, new termbase, new contents. Terminologija 26: 6–23. DOI logoGoogle Scholar
Chiocchetti, Elena, Ralli, Natascia & Stanizzi, Isabella
2017 From DIY translations to official standardisation and back again? 50 years of experience with Italian and German legal terminology work in South Tyrol. In Terms and Terminology in the European Context, Paola Faini (ed.), 254–270. Newcastle upon Tyne: Cambridge Scholars.Google Scholar
Contarino, Antonio Giovanni
2021 Neural Machine Translation Adaptation and Automatic Terminology Evaluation: A Case Study on Italian and South Tyrolean German Legal Texts. Master’s dissertation, University of Bologna. [URL]> (30 May 2023).
De Camillis, Flavia
2021 La traduzione non professionale nelle istituzioni pubbliche dei Territori di lingua minoritaria: Il caso di studio dell’amministrazione della Provincia Autonoma di Bolzano. PhD dissertation, University of Bologna. [URL]> (30 May 2023).
Dougal, Duane K. & Lonsdale, Deryle
2020 Improving NMT quality using terminology injection. In Proceedings of the 12th Language Resources and Evaluation Conference, 4820–4827. Marseille: European Language Resources Association. [URL] (30 May 2023).
DPR 670/1972
. Decreto del Presidente della Repubblica 31 agosto 1972, n. 670 “Approvazione del testo unico delle leggi costituzionali concernenti lo statuto speciale per il Trentino – Alto Adige”. [URL]> (30 May 2023).
Farajian, M. Amin, Bertoldi, Nicola, Negri, Matteo, Turchi, Marco & Federico, Marcello
2018 Evaluation of terminology translation in instance-based neural MT adaptation. In Proceedings of the 21st Annual Conference of the European Association for Machine Translation, Juan Antonio Pérez-Ortiz, Felipe Sánchez-Martínez, Miquel Esplà-Gomis, Maja Popović et al. (eds), 149–158. Alicante: European Association for Machine Translation. [URL] (30 May 2023).
Haque, Rejwanul, Hassanuzzman, Mohammed & Way, Andy
2019 Terminology Translation in Low-Resource Scenarios. Information 10 (9), 273, 1–28. DOI logoGoogle Scholar
Heiss, Christine & Soffritti, Marcello
2018 DeepL traduttore e didattica della traduzione dall’italiano in tedesco. In Translation And Interpreting for Language Learners (TAIL). Special issue of inTRAlinea, 1–11. [URL]> (30 May 2023).
Koehn, Philipp
2004 Statistical significance tests for machine translation evaluation. In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing, Dekang Lin & Dekai Wu (eds), 388–395. Barcelona: Association for Computational Linguistics. [URL] (30 May 2023).
Koehn, Philipp & Knowles, Rebecca
2017 Six challenges for neural machine translation. In Proceedings of the First Workshop on Neural Machine Translation, Thang Luong, Alexandra Birch, Graham Neubig & Andrew Finch (eds), 28–39. Vancouver: Association for Computational Linguistics. [URL]> (30 May 2023) DOI logoGoogle Scholar
Marie, Benjamin, Fujita, Atsushi & Rubino, Raphael
2021 Scientific credibility of machine translation research: A meta-evaluation of 769 papers. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Vol. 1: Long Papers, 7297–7306. Stroudsburg PA: Association for Computational Linguistics. DOI logo (30 May 2023)
Papineni, Kishore, Roukos, Salim, Ward, Todd & Zhu, Wei-Jing
2002 Bleu: A method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, Pierre Isabelle, Eugene Charniak & Dekang Lin (eds), 311–318. Stroudsburg PA: Association for Computational Linguistics. DOI logoGoogle Scholar
Popović, Maja
2015 ChrF: Character n-gram F-score for automatic MT evaluation. In Proceedings of the Tenth Workshop on Statistical Machine Translation, Ondřej Bojar, Rajan Chatterjee, Christian Federmann, Barry Haddow et al. (eds), 392–395. Lisbon: Association for Computational Linguistics. DOI logoGoogle Scholar
Post, Matt
2018 A call for clarity in reporting BLEU scores. In Proceedings of the Third Conference on Machine Translation: Research Papers, Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Mark Fishel et al. (eds), 186–191. Brussels: Association for Computational Linguistics DOI logo
Ralli, Natascia & Andreatta, Norbert
2018 bistro – ein Tool für mehrsprachige Rechtsterminologie. trans-kom 11(1):7–44. [URL]> (30 May 2023)Google Scholar
Saunders, Danielle
2021 Domain adaptation and multi-domain adaptation for neural machine translation: A survey. CoRR abs/2104.06951. [URL]> (30 May 2023).Google Scholar
van der Wees, Marlies
2017 What’s in a Domain?: Towards Fine-grained Adaptation for Machine Translation. PhD dissertation, University of Amsterdam. [URL]> (30 May 2023).
Varga, Daniel, Halacsy, Peter, Kornai, Andras, Nagy, Viktor, Nemeth, Laszlo & Tron, Viktor
2007 Parallel corpora for medium density languages. In Recent Advances in Natural Language Processing IV: Selected papers from RANLP 2005 [Current Issues in Linguistic Theory 292], Nicolas Nicolov, Kalina Bontcheva, Galia Angelova & Ruslan Mitkov (eds), 247–258. Amsterdam: John Benjamins. DOI logoGoogle Scholar
Wiesmann, Eva
2019 Machine translation in the field of law: A study of the translation of Italian legal texts into German. Comparative Legilinguistics 37:117–53. DOI logoGoogle Scholar
Woelk, Jens
2000 Von ‘Advokat’ bis ‘Zentraldirektion der Autonomien’. Die Südtiroler Rechtssprache aus Sicht eines ‘bundesdeutschen’ Juristen. In Linguistica giuridica italiana e tedesca, Daniela Veronesi (ed.), 209–222. Padova: Unipress.Google Scholar